© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97769
    Prev
    Next
    INDEX
    Explanations

    try

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tents
    -0.31
    halt
    -0.28
    .geo
    -0.25
    èĥĮåIJİçļĦ
    -0.25
    totals
    -0.24
    /Getty
    -0.24
    arently
    -0.23
    éģŃ
    -0.23
    urette
    -0.23
    .coordinate
    -0.23
    POSITIVE LOGITS
     individual
    0.30
     Aspect
    0.26
    매
    0.26
     rep
    0.26
     messing
    0.26
    kee
    0.25
    马åħĭæĢĿ
    0.25
     lump
    0.24
     incom
    0.24
    ew
    0.23
    Activations Density 0.119%

    No Known Activations